The Annals of Statistics
- Ann. Statist.
- Volume 46, Number 1 (2018), 247-279.
High-dimensional asymptotics of prediction: Ridge regression and classification
We provide a unified analysis of the predictive risk of ridge regression and regularized discriminant analysis in a dense random effects model. We work in a high-dimensional asymptotic regime where $p,n\to\infty$ and $p/n\to\gamma>0$, and allow for arbitrary covariance among the features. For both methods, we provide an explicit and efficiently computable expression for the limiting predictive risk, which depends only on the spectrum of the feature-covariance matrix, the signal strength and the aspect ratio $\gamma$. Especially in the case of regularized discriminant analysis, we find that predictive accuracy has a nuanced dependence on the eigenvalue distribution of the covariance matrix, suggesting that analyses based on the operator norm of the covariance matrix may not be sharp. Our results also uncover an exact inverse relation between the limiting predictive risk and the limiting estimation risk in high-dimensional linear models. The analysis builds on recent advances in random matrix theory.
Ann. Statist., Volume 46, Number 1 (2018), 247-279.
Received: December 2015
Revised: November 2016
First available in Project Euclid: 22 February 2018
Permanent link to this document
Digital Object Identifier
Mathematical Reviews number (MathSciNet)
Zentralblatt MATH identifier
Dobriban, Edgar; Wager, Stefan. High-dimensional asymptotics of prediction: Ridge regression and classification. Ann. Statist. 46 (2018), no. 1, 247--279. doi:10.1214/17-AOS1549. https://projecteuclid.org/euclid.aos/1519268430
- Supplement to “High-dimensional asymptotics of prediction: Ridge regression and classification”. In the supplementary material, we give efficient methods to compute the risk formulas, and prove the remaining lemmas and other results.